Raw Speech-to-Articulatory Inversion by Temporal Filtering and Decimation.
Abdolreza Sabzi ShahrebabakiSabato Marco SiniscalchiTorbjørn SvendsenPublished in: Interspeech (2021)
Keyphrases
- temporal filtering
- speech recognition
- vocal tract
- speech signal
- speech synthesis
- spatial filtering
- multi stream
- motion detection
- image sequences
- motion estimation
- acoustic features
- formant frequencies
- automatic speech recognition
- video coding
- text to speech
- audio visual
- linear prediction
- hidden markov models
- language model
- mathematical morphology
- motion compensation
- texture analysis
- optical flow
- multiscale
- image processing